Jichi Chen

Fatigue driving is one of the primary factors that contribute to road traffic accidents worldwide and poses a serious threat to transportation safety as well as to public life and property. To achieve accurate and efficient detection of driver fatigue while the complex and nonlinear characteristics of physiological signals are adequately represented, this study proposes a detection framework that is based on multi-band electroencephalography (EEG) feature optimization and a support vector machine (SVM). The EEG signals are decomposed into the θ (4–8 Hz), α (8–14 Hz), β (14–30 Hz), and full-band (1–50 Hz) components, from which time-domain, frequency-domain, nonlinear dynamic, and brain network connectivity features are extracted so that a high-dimensional feature space with multi-scale and multi-structural information can be constructed. To reduce redundancy and enhance discriminative capability, a three-stage feature optimization strategy is adopted, in which variance inflation factor analysis is applied to remove multicollinearity, mutual information is used to identify features with strong discriminative power, and SVM-based recursive feature elimination SVM is employed to further compress the feature space. Fatigue states are then identified by SVM classifiers that are constructed with different kernel functions, and the detection performance across frequency bands is systematically evaluated. Experiments are conducted on a publicly available driving EEG dataset, and the results demonstrate that the β -band features combined with a medium Gaussian kernel SVM achieve the best performance. Under cross-validation, the proposed method attains an accuracy of 86.34%, a precision of 88.89%, a sensitivity of 83.06%, an F 1-score of 85.87%, and a false detection rate of 10.38%. These results indicate that the proposed framework effectively captures the complex EEG patterns associated with driver fatigue and provides a robust solution for fatigue detection.

Driver fatigue has been identified as one of the primary causes of traffic accidents. As long‐duration and high‐load driving becomes increasingly common, the risks of delayed reactions and impaired distance judgment continue to rise. Traditional behavior‐based methods for detecting driver fatigue often exhibit limited stability in complex driving environments. In contrast, electroencephalography (EEG) offers a more reliable detecting method by directly capturing central nervous system activity. This work focuses on fatigue driving detection based on deep learning and EEG, which outlines commonly used public datasets, key preprocessing techniques, feature extraction techniques, performance evaluation metrics, and mainstream deep learning architectures. Based on research progress over the past three years, the use of datasets, published journals, research challenges, and limitations of current methods were analyzed. Future research should improve the model's generalization ability and robustness, introduce richer brain network features, and construct a larger‐scale, high‐quality dataset that closely resembles the real driving environment.

Bearing fault diagnosis is crucial for ensuring the safe and stable operation of industrial systems, as key components in rotating machinery. To address the problem that traditional methods rely on manual feature engineering and have limited accuracy, this study proposes a novel bearing fault diagnosis method based on a combination of time-frequency analysis, deep feature extraction, feature dimensionality reduction and machine learning. First, wavelet synchrosqueezed transform (WSST) is used to transform the one-dimensional signal into a time-frequency image to obtain rich and robust time-frequency representation. Then, the DenseNet-201 pre-trained deep learning model is used for deep feature extraction. Finally, the bearing fault diagnosis performance of nine cases consisting of three dimensionality reduction methods and three machine learning methods is systematically evaluated. Experimental results show that the WSST method performs best in feature representation, DenseNet-201 performs best in deep feature extraction, and Case achieves the best bearing fault diagnosis performance under ten-fold cross-validation, with an average accuracy of 98.56%, which is superior to existing state-of-the-art methods. The novel bearing fault diagnosis method proposed in this study not only has advantages in accuracy and stability, but also shows good potential for engineering applications.

Lower limb motion recognition plays a vital role in intelligent prosthetic control and wearable assistance systems. While traditional methods typically utilize multi-channel surface electromyography (sEMG) signals to ensure recognition performance, such systems often involve complex hardware setups, are uncomfortable to wear, and require high computational resources. To address these challenges, this study aims to develop an efficient, low-complexity motion recognition approach based on single-channel sEMG signals. The proposed method integrates fast iterative filtering decomposition (FIFD) with a hybrid deep learning framework. FIFD is employed to decompose raw single-channel sEMG signals into multiple sub-components, allowing the extraction of informative intrinsic features. These features are then processed by a deep neural network that combines convolutional neural networks (CNN), attention mechanisms, and long short-term memory (LSTM) units to jointly capture spatial and temporal characteristics of the sEMG signal. Experiments were conducted on a self-constructed dataset comprising sEMG recordings of lower limb movements. The proposed method achieved a recognition accuracy of 99.35%, outperforming conventional multi-channel approaches and other baseline models. The model demonstrated strong robustness and generalizability using only single-channel input. This study presents a novel single-channel sEMG motion recognition method that significantly reduces system complexity while maintaining high recognition accuracy. The approach offers a promising solution for developing low-cost, efficient, and user-friendly wearable systems, particularly suitable for lower limb rehabilitation and human-computer interaction in resource-constrained environments.

Epilepsy is a prevalent neurological disorder that demands accurate and efficient detection for effective clinical management. Electroencephalogram (EEG) signals provide a non-invasive, low-cost, and high -temporal resolution means of monitoring brain activity, which makes it particularly suitable for epileptic seizure detection. However, conventional detection methods that rely on manual feature extraction or expert interpretation are often labor-intensive, subjective, and lack generalization capability. To address these limitations, this study proposes a novel automatic epileptic seizure detection framework that integrates deep feature extraction with machine learning. First, Short-Time Fourier Transform is applied to perform time-frequency analysis and capture local dynamic features of EEG signals. Then, pre-trained deep learning models are employed to extract deep features, which enhances the representation of the EEG signals. Finally, these deep features are fed into machine learning for epileptic seizure detection. Experiments are conducted on two publicly available EEG datasets, the Bonn EEG dataset and the New Delhi EEG dataset. The results indicate that fusing deep features from multiple pre-trained deep learning models enhances the overall detection accuracy. This study presents an effective and novel method for automatic epileptic seizure detection using EEG signals. The combination of deep feature extraction and machine learning provides new insights into the detection of neurological disorders through deep learning techniques.